ROS Robotics Projects by Lentin Joseph

Author:Lentin Joseph [Joseph, Lentin]
Language: eng
Format: azw3
Publisher: Packt Publishing
Published: 2017-03-31T04:00:00+00:00

After uploading the model, we have to train it. You can use the following command: $ rosrun object_recognition_core training -c `rospack find object_recognition_linemod`/conf/training.ork

If the training is successful, you will see a message like this:

Figure 17: Training 3D objects

Training from captured 3D models

If you don't have a 3D mesh of the object, you can also create one by capturing the 3D point cloud data and reconstructing the mesh. Here are the steps to capture and build the mesh of an object:

Before the capture, we have to print a pattern for better capturing and reconstruction. You can download the pattern from http://wg-perception.github.io/capture/_downloads/capture_board_big_5x3.svg.pdf.

Download

Copyright Disclaimer:
This site does not store any files on its server. We only index and link to content provided by other sites. Please contact the content providers to delete copyright contents if any and email us, we'll remove relevant links or contents immediately.